{"id":"https://openalex.org/W7134178881","doi":"https://doi.org/10.1109/bigdata66926.2025.11402368","title":"Leveraging Machine Learning and Large Language Models for Automated Image Clustering and Description in Legal Discovery","display_name":"Leveraging Machine Learning and Large Language Models for Automated Image Clustering and Description in Legal Discovery","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7134178881","doi":"https://doi.org/10.1109/bigdata66926.2025.11402368"},"language":null,"primary_location":{"id":"doi:10.1109/bigdata66926.2025.11402368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11402368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128359776","display_name":"Qiang Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137080","display_name":"University Legal Services","ror":"https://ror.org/03s8rh204","country_code":"US","type":"education","lineage":["https://openalex.org/I4210137080"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Mao","raw_affiliation_strings":["Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,Washington D.C.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,Washington D.C.,USA","institution_ids":["https://openalex.org/I4210137080"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052463733","display_name":"Fusheng Wei","orcid":"https://orcid.org/0009-0000-5881-5307"},"institutions":[{"id":"https://openalex.org/I4210137080","display_name":"University Legal Services","ror":"https://ror.org/03s8rh204","country_code":"US","type":"education","lineage":["https://openalex.org/I4210137080"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fusheng Wei","raw_affiliation_strings":["Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,Washington D.C.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,Washington D.C.,USA","institution_ids":["https://openalex.org/I4210137080"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042371258","display_name":"Robert Neary","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137080","display_name":"University Legal Services","ror":"https://ror.org/03s8rh204","country_code":"US","type":"education","lineage":["https://openalex.org/I4210137080"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Neary","raw_affiliation_strings":["Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,Washington D.C.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,Washington D.C.,USA","institution_ids":["https://openalex.org/I4210137080"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128351729","display_name":"Charles Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137080","display_name":"University Legal Services","ror":"https://ror.org/03s8rh204","country_code":"US","type":"education","lineage":["https://openalex.org/I4210137080"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Wang","raw_affiliation_strings":["Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,Washington D.C.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,Washington D.C.,USA","institution_ids":["https://openalex.org/I4210137080"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101414673","display_name":"Han Qin","orcid":"https://orcid.org/0000-0001-9776-5007"},"institutions":[{"id":"https://openalex.org/I4210137080","display_name":"University Legal Services","ror":"https://ror.org/03s8rh204","country_code":"US","type":"education","lineage":["https://openalex.org/I4210137080"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Qin","raw_affiliation_strings":["Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,Washington D.C.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,Washington D.C.,USA","institution_ids":["https://openalex.org/I4210137080"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128331927","display_name":"Jianping Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137080","display_name":"University Legal Services","ror":"https://ror.org/03s8rh204","country_code":"US","type":"education","lineage":["https://openalex.org/I4210137080"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianping Zhang","raw_affiliation_strings":["Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,Washington D.C.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,Washington D.C.,USA","institution_ids":["https://openalex.org/I4210137080"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049186333","display_name":"Nathaniel Huber-Fliflet","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142469","display_name":"Health Data Research UK","ror":"https://ror.org/04rtjaj74","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210142469"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nathaniel Huber-Fliflet","raw_affiliation_strings":["Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ankura Consulting Group, LLC,Legal Technology &#x0026; Data Analytics,London,UK","institution_ids":["https://openalex.org/I4210142469"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86209122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7556","last_page":"7561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.5891000032424927,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.5891000032424927,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.03880000114440918,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13904","display_name":"Artificial Intelligence Applications","score":0.0215000007301569,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5842999815940857},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3562000095844269},{"id":"https://openalex.org/keywords/conceptual-clustering","display_name":"Conceptual clustering","score":0.3515999913215637},{"id":"https://openalex.org/keywords/computational-learning-theory","display_name":"Computational learning theory","score":0.33320000767707825},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3118000030517578},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.30799999833106995},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.29409998655319214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300999760627747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6640999913215637},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5842999815940857},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5001999735832214},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3625999987125397},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.3515999913215637},{"id":"https://openalex.org/C50292564","wikidata":"https://www.wikidata.org/wiki/Q2462783","display_name":"Computational learning theory","level":3,"score":0.33320000767707825},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26910001039505005},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata66926.2025.11402368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11402368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2011430131","https://openalex.org/W2194775991","https://openalex.org/W2963037989","https://openalex.org/W4236645963","https://openalex.org/W7133224126"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-09T00:00:00"}
